Home

Pattern Recognition and Image Processing

Dept. of Computer Science Faculty of Engineering

Datasets

Binaries/Code Datasets Open Source Software

Freiburg-Berkeley Motion Segmentation Dataset

Video Segmentation Benchmark

Image Sequences

TILDA Textile Texture Database

Training data for Exemplar CNN

Generated Matching Dataset

Training data for chair generation

Stereo Ego-motion Dataset

Optical Flow Datasets: "Flying Chairs", "ChairsSDHom"

Scene Flow Datasets

Human Part Segmentation Datasets

Rendered Handpose Dataset

Pedestrian Zone Scene

FreiHAND Dataset

Human Pose RGBD Datasets

OVAD: Open-Vocabulary Attribute Detection Dataset

ADE-OoD: a benchmark for dense Out-of-Distribution detection on natural images.

Pedestrian Zone Scene

preview

This dataset contains images of a street sign. The scene poses several challenges to reconstruction algorithms:

Objects with small volume (sign, posts)
Reflections and small regions with low texture

Download

Terms of use

The dataset is provided for research purposes. Any commercial use is prohibited. When using the dataset in your research work, cite the following paper:

B. Ummenhofer and T. Brox, "Point-Based 3D Reconstruction of Thin Objects," in 2013 IEEE International Conference on Computer Vision, 2013, pp. 969-976.